Commit Graph

1996 Commits

Author SHA1 Message Date
yh_cc
7dcc6d301d collator可自动判断collate的backend 2022-05-02 17:10:58 +08:00
yh_cc
275a4ba129 Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-05-02 15:39:23 +08:00
yh_cc
4ed012bf1a 更新cache_results的测试 2022-05-02 15:39:15 +08:00
x54-729
2797c0a961 删除不必要的文件 2022-05-02 05:48:10 +00:00
x54-729
4bfb509f12 调整测试例以适应pytest;为测试例添加标签 2022-05-02 05:46:47 +00:00
yh_cc
d645e88c7f 1.增加部分padder的注释;2.修改set_backend的位置 2022-05-01 23:17:56 +08:00
MorningForest
ac61430aa1 Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-05-01 17:19:50 +08:00
MorningForest
0510f31a5e 增加pytest.mark.torch or paddle标记 2022-05-01 17:19:42 +08:00
YWMditto
8ea8992a47 MERGE 2022-05-01 16:57:57 +08:00
YWMditto
26397472aa 加入了 @pytest.mark.torch 2022-05-01 16:53:46 +08:00
MorningForest
6b7b062cec Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-05-01 14:08:08 +08:00
yh_cc
9d2dc748ea merge 2022-05-01 00:33:10 +08:00
yh_cc
b38fc1136e 1.修改ProgressBart在Trainer中的一个bug;2修复pytest的bug 2022-05-01 00:32:11 +08:00
lxr-tech
040dfa654a Merge branch 'dev0.8.0' of https://github.com/fastnlp/fastNLP into dev0.8.0 2022-04-30 23:29:23 +08:00
lxr-tech
6da627d4ce modify-fastnlp_tutorial_0-lxr-220430 2022-04-30 23:29:12 +08:00
YWMditto
0500682191 Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-30 21:39:35 +08:00
YWMditto
35f0593268 修改了一些测试文件的名称 2022-04-30 21:39:20 +08:00
x54-729
cf2ef2ecd7 调整测试例的backend设置 2022-04-30 13:04:55 +00:00
x54-729
b3c9819fb8 添加 __init__.py 2022-04-30 12:55:57 +00:00
x54-729
a6103f6342 重命名不需要pytest的测试文件 2022-04-30 10:51:55 +00:00
yh_cc
b78cea7ff9 Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-30 17:10:11 +08:00
yh_cc
b3e0ebd7fc 优化了Collator 2022-04-30 17:10:03 +08:00
x54-729
df0651baae 删除 transformers 中的依赖包字典 2022-04-30 09:00:29 +00:00
x54-729
df1db2535a 迁移transformers ver.4.11.3的bert bart roberta gpt2和cpt模型 2022-04-29 16:53:02 +00:00
MorningForest
1216ac6e90 Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-30 00:22:38 +08:00
MorningForest
39e199467a accuracy修改 2022-04-30 00:22:29 +08:00
yh_cc
2dc1199402 Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-29 22:24:55 +08:00
yh_cc
d4dd85ed40 新设计collator 2022-04-29 22:24:46 +08:00
lxr-tech
29fb454c2e modify fastnlp_tutorial_0.py 2022-04-29 22:22:28 +08:00
YWMditto
ba8971fcf3 little change 2022-04-29 18:19:07 +08:00
yh_cc
f74b9b6bec 修改所有的 validate 为 evaluate ; 移动 callback.on_train_end() 2022-04-28 16:27:17 +08:00
yh_cc
b3bc58b0bb Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-28 15:12:30 +08:00
yh_cc
0043e3e89a 修复LoadeBestModelCallback的bug 2022-04-28 15:12:21 +08:00
x54-729
f319b5bce1 torch ddp 的测试用例 2022-04-26 05:49:32 +00:00
x54-729
df109316e5 small 2022-04-26 05:33:37 +00:00
x54-729
d04f49a835 修改BucketedBatchSampler batch_idx_in_epoch 的计算方式,使其在分布式条件下可以正确地反应迭代次数 2022-04-26 05:33:17 +00:00
x54-729
822df062ca 添加函数的注释 2022-04-26 05:31:45 +00:00
x54-729
705deeaea9 small 2022-04-26 03:35:25 +00:00
x54-729
cf65da1332 paddle 单卡测试例调整 2022-04-25 12:58:03 +00:00
x54-729
bb10410ccd torch 单卡的测试例 2022-04-25 12:57:17 +00:00
yh_cc
6f7bbfabca 增加部分关于evaluate_batch_step_fn的说明 2022-04-25 19:35:49 +08:00
yh_cc
7e40d98404 新增train_input_mapping 和 evaluate_input_mapping 等 2022-04-25 16:47:29 +08:00
yh_cc
6ddcedaaeb Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-24 12:09:35 +08:00
yh_cc
e85cbb067e Rich支持jupyter 2022-04-24 12:09:19 +08:00
YWMditto
711bbf469c 修改了 trainer.load_model/load 只有单卡加载的bug 2022-04-23 14:44:18 +08:00
yh_cc
1ecbdc7446 修复TopkSaver在CheckpointCallbackk中的bug;修改Saver对象,使得其方便被直接使用 2022-04-23 00:41:12 +08:00
yh_cc
b117f6170c Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-22 02:09:43 +08:00
yh_cc
ceb30937b8 更新Trainer的部分文档; 更新topk_saver文档 2022-04-22 02:09:30 +08:00
x54-729
c74da391c7 跟进paddle backend关于all_gather的改动 2022-04-20 10:27:09 +00:00
x54-729
fcc45dbf4a PaddleFleetDriver添加all_gather和broadcast_object函数 2022-04-20 10:17:19 +00:00